Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10280
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names associated with notable entities and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.92
    ounter
    -0.83
    elaide
    -0.79
    izabeth
    -0.78
    istically
    -0.77
    aturally
    -0.75
    livion
    -0.74
    ocobo
    -0.74
    ITY
    -0.70
     earth
    -0.69
    POSITIVE LOGITS
     Maker
    0.93
    Maker
    0.91
     Stop
    0.85
    breaker
    0.85
     Away
    0.84
     Stall
    0.84
    atoon
    0.83
     Alley
    0.82
     Shack
    0.82
    Pad
    0.82
    Activations Density 0.056%

    No Known Activations